{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/diffusiondb-a-large-scale-prompt-gallery","title":"DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models","arxiv_id":"2210.14896","date":"2022-10-26","proceeding":null,"authors":["Zijie J. Wang","Evan Montoya","David Munechika","Haoyang Yang","Benjamin Hoover","Duen Horng Chau"],"abstract":"With recent advancements in diffusion models, users can generate high-quality images by writing text prompts in natural language. However, generating images with desired details requires proper prompts, and it is often unclear how a model reacts to different prompts or what the best prompts are. To help researchers tackle these critical challenges, we introduce DiffusionDB, the first large-scale text-to-image prompt dataset totaling 6.5TB, containing 14 million images generated by Stable Diffusion, 1.8 million unique prompts, and hyperparameters specified by real users. We analyze the syntactic and semantic characteristics of prompts. We pinpoint specific hyperparameter values and prompt styles that can lead to model errors and present evidence of potentially harmful model usage, such as the generation of misinformation. The unprecedented scale and diversity of this human-actuated dataset provide exciting research opportunities in understanding the interplay between prompts and generative models, detecting deepfakes, and designing human-AI interaction tools to help users more easily use these models. DiffusionDB is publicly available at: https://poloclub.github.io/diffusiondb.","url_abs":"https://arxiv.org/abs/2210.14896v4","url_pdf":"https://arxiv.org/pdf/2210.14896v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"diffusiondb-a-large-scale-prompt-gallery","repo_url":"https://github.com/poloclub/diffusiondb","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"diffusiondb-a-large-scale-prompt-gallery","repo_url":"https://github.com/kenjiqq/aesthetics-scorer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"misinformation","task_name":"Misinformation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[{"slug":"diffusiondb","name":"DiffusionDB","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.14896","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.14896"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/poloclub/diffusiondb","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kenjiqq/aesthetics-scorer","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":8},"by_repo_kind":{"listed":{"samples":8,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"18d8cfd195fc545d","entry":"acc","repo":"kenjiqq/aesthetics-scorer","repo_kind":"listed","path":"benchmark/benchmark_imagereward.py","file_url":"https://github.com/kenjiqq/aesthetics-scorer/blob/HEAD/benchmark/benchmark_imagereward.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"18d8cfd195fc545d"}},{"code_sha256_prefix":"ac8437e23e0c25d7","entry":"fancy_round","repo":"kenjiqq/aesthetics-scorer","repo_kind":"listed","path":"dataset-process/dataset_parquet_files.py","file_url":"https://github.com/kenjiqq/aesthetics-scorer/blob/HEAD/dataset-process/dataset_parquet_files.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ac8437e23e0c25d7"}},{"code_sha256_prefix":"32ae2c776cdca3a6","entry":"flatten_nested_list","repo":"kenjiqq/aesthetics-scorer","repo_kind":"listed","path":"benchmark/benchmark_imagereward.py","file_url":"https://github.com/kenjiqq/aesthetics-scorer/blob/HEAD/benchmark/benchmark_imagereward.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"32ae2c776cdca3a6"}},{"code_sha256_prefix":"1c591746911cb868","entry":"get_transforms","repo":"kenjiqq/aesthetics-scorer","repo_kind":"listed","path":"convnext_scorer/model.py","file_url":"https://github.com/kenjiqq/aesthetics-scorer/blob/HEAD/convnext_scorer/model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1c591746911cb868"}},{"code_sha256_prefix":"7772439645a30818","entry":"load_model","repo":"kenjiqq/aesthetics-scorer","repo_kind":"listed","path":"aesthetics_scorer/model.py","file_url":"https://github.com/kenjiqq/aesthetics-scorer/blob/HEAD/aesthetics_scorer/model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7772439645a30818"}},{"code_sha256_prefix":"3460308a8cb85ca3","entry":"load_model","repo":"kenjiqq/aesthetics-scorer","repo_kind":"listed","path":"convnext_scorer/model.py","file_url":"https://github.com/kenjiqq/aesthetics-scorer/blob/HEAD/convnext_scorer/model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3460308a8cb85ca3"}},{"code_sha256_prefix":"d9a92415aa7126f1","entry":"preprocess","repo":"kenjiqq/aesthetics-scorer","repo_kind":"listed","path":"aesthetics_scorer/model.py","file_url":"https://github.com/kenjiqq/aesthetics-scorer/blob/HEAD/aesthetics_scorer/model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d9a92415aa7126f1"}},{"code_sha256_prefix":"4e875f63f7b3ec35","entry":"restore_nested_list","repo":"kenjiqq/aesthetics-scorer","repo_kind":"listed","path":"benchmark/benchmark_imagereward.py","file_url":"https://github.com/kenjiqq/aesthetics-scorer/blob/HEAD/benchmark/benchmark_imagereward.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4e875f63f7b3ec35"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}